These are the Meta models currently listed as live in the Borg directory. The descriptions below summarize each model's published use cases; the linked model pages give the full account. A lane id is the value you use to select a model directly in the Borg gateway, not a separate model name. Check the linked pages for context windows, reasoning support and any vendor API list prices before choosing a lane for your work.
Muse Spark 1.1 was the first Muse Spark version offered to developers through Meta Model API, succeeding the original Muse Spark shown in Meta AI.
Best for Muse Spark 1.1:
computer-use agents spanning several applications
debugging interfaces from screenshots
multimodal document and video analysis
multi-agent task planning with long histories
Borg lane ids: muse-spark-1.1, meta/muse-spark-1.1. Open the model page for its full description, available specifications, vendor price sources, and routing roles.
Muse Spark 1.2 is the coding-focused successor to 1.1, co-trained with Meta's Muse Code agent for long-running software work.
Best for Muse Spark 1.2:
multi-file refactors in large repositories
long debugging sessions with tool calls
agentic code generation and validation
understanding codebases and dependency graphs
Borg lane ids: muse-spark-1.2, meta/muse-spark-1.2. Open the model page for its full description, available specifications, vendor price sources, and routing roles.
Muse Spark 1.3 is the newest version of Meta's Muse Spark reasoning line.
Best for Muse Spark 1.3:
long-horizon coding with changing requirements
multi-step browser and tool workflows
large-context instruction following
reasoning-intensive repository tasks
Borg lane ids: muse-spark-1.3, meta/muse-spark-1.3. Open the model page for its full description, available specifications, vendor price sources, and routing roles.
How Fusion uses Meta
Borg Fusion can route between models in the subscription catalog according to the task and the selected profile. Having a Meta lane in the catalog does not mean that every Fusion profile will choose it for every request. No specific routing assignments for Meta are published in this catalog. The model pages distinguish published routing roles from use cases, so you can compare options without assuming a benchmark result or a routing guarantee. You can also choose a listed lane directly if you want to control which model handles a request.
FAQ
Which Meta models are in Borg?
The table and model details above list the current live Meta models in Borg. Each linked page includes the model's lane ids and available specifications. Models awaiting identity review are not shown as live.
How does Fusion use Meta?
Fusion profiles select from available lanes depending on the task. Consult each Meta model page for its published Fusion roles; a missing role is not evidence that the model cannot be selected directly.
Can I select a Meta lane directly?
Yes. Open a Meta model page to find its Borg lane ids and the compatible gateway model field. Use the lane id rather than the public page slug when choosing a model directly.
Meta
Anthropic
OpenAI
Google
xAI
Moonshot AI
Z.ai